INDEX

Explanations

phrases related to frequency or repetition

oai_token-act-pair · gpt-3.5-turbo

the word "every."

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.3.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

olas

-0.76

phabet

-0.73

 Metatron

-0.67

zai

-0.66

dict

-0.66

Viz

-0.64

hess

-0.62

 notwithstanding

-0.61

Osw

-0.61

Ü

-0.58

POSITIVE LOGITS

THING

1.44

 conceivable

1.03

where

0.98

single

0.95

 imaginable

0.92

 single

0.91

things

0.90

WHERE

0.87

Ĥª

0.82

body

0.81

Activations Density 0.044%

phrases related to frequency or repetition

the word "every."

No Comments

No Known Activations